© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69976
    Prev
    Next
    INDEX
    Explanations

    fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     khusus
    -0.08
     aż
    -0.08
    emers
    -0.08
     lave
    -0.08
    _launcher
    -0.07
     ngaj
    -0.07
     Chil
    -0.07
     scel
    -0.07
     voire
    -0.07
     issu
    -0.07
    POSITIVE LOGITS
    band
    0.09
    matches
    0.08
    ව
    0.08
    margin
    0.07
    裤
    0.07
     Band
    0.07
    igheter
    0.07
    355
    0.07
    fur
    0.07
     Burr
    0.07
    Activations Density 0.031%

    No Known Activations